Lightning-fast last-mile route optimization API

Stop paying
per stop.
Pay per solve.

Raiden solves VRP at Rust speed using adaptive large neighborhood search. Pay for the compute seconds your problem uses. Not for routes, not for stops, not for vehicles.

// initializing solver...
<10ms
Median solve time, 100 stops
P99 <40ms · written in Rust
15%
Avg cost reduction vs greedy baseline
ALNS + simulated annealing
$0
Per stop. Per route. Per vehicle.
Compute-unit pricing only. Industry first.
Used by engineering teams at
Acme Logistics FleetCo DeliverX RouteWorks LastMile.io
// the problem with everyone else

Competitors bill you
for your own growth.

Per-stop and per-route pricing means scaling your delivery operation directly inflates your API bill. Raiden charges for the CPU seconds your solve actually consumed. Nothing more.

Traditional VRP APIs

LEGACY PRICING

⚡ RAIDEN

DIFFERENT BY DESIGN

Per-stop pricing

1,000 stops/day costs 10× more than 100. Every order you win raises your infrastructure bill.

Compute-unit pricing only

Solve 100 stops or 10,000: your unit cost is the same. Scale routes, not bills.

Per-vehicle / per-route limits

Expanding your fleet forces a plan upgrade mid-contract.

Unlimited vehicles & routes

No fleet-size limits. Add vans, add shifts. Raiden doesn't count vehicles.

Black-box solvers

No visibility into solution quality, iteration counts, or why a route looks the way it does.

Published benchmark results

CVRPLIB and Solomon VRPTW scores are public. Judge quality before you integrate.

Enterprise gate

Real limits are behind "contact sales." Developers can't prototype without a meeting.

Public pricing, free tier, no sales call

Start prototyping in minutes. No demo required to see real limits.

Generic VRP solvers

Last-mile specifics (time windows, service time, committed stops) are afterthoughts.

Last-mile native

Time windows, capacity, service duration, committed-stop locking: all first-class.

// developer-first

Integrate in minutes,
not sprints.

A clean REST API. No SDK required. POST your stops, GET optimized routes. Every response includes cost, timing, and solve diagnostics.

optimize.sh
# Optimize 100 stops across 3 vehicles with time windows
curl https://api.raiden.dev/v1/optimize \
  -H "Authorization: Bearer $RAIDEN_KEY" \
  -H "Content-Type: application/json" \
  -d 
    "depot":     "lat": 51.5074, "lng": -0.1278 ,
    "vehicles": [
       "id": "van_1", "capacity": 800,
        "shift": ["08:00", "18:00"] 
    ],
    "stops": [
       "id": "order_291", "lat": 51.52, "lng": -0.09,
        "demand": 12, "window": ["09:00", "12:00"],
        "service_min": 5 
      /* ... 99 more stops */
    ]
  

# Response in ~8ms:

  "routes": [
    "vehicle":   "van_1",
    "stops":    ["order_291", "..."],
    "eta_each": ["09:11", "..."],
    "total_km": 91.4
  ],
  "unassigned":  [],
  "compute_ms":  8,
  "cost_usd":    0.0003,
  "iterations":  6821

Sub-second for 500 stops

Rust-native ALNS with simulated annealing. Warm-start support for recurring daily routes.

🕐

Time windows are first-class

Savelsbergh forward-slack timing arrays. O(1) feasibility checks. Hard and soft windows both supported.

🔒

Committed-stop locking

Mark stops as in-progress mid-day and re-optimize the rest without touching locked assignments.

🔬

Transparent diagnostics

Every response returns iteration count, operator scores, and solution cost breakdown. No black box.

// try it now

Drop some stops.
Watch Raiden solve.

Click to add delivery stops. Drag to move them. Routes update instantly.

Click anywhere to add a stop
// capabilities

Built for last-mile.
Not bolted on.

🚐

Multi-vehicle CVRPTW

Heterogeneous fleets with per-vehicle capacity, shift hours, and speed profiles. Hard time windows enforced.

CVRPTW

Time Windows

Customer delivery windows with service duration per stop. Earliest departure, latest arrival, all exact.

VRPTW
🔄

Dynamic Re-optimization

New order dropped? Cancellation received? Re-solve in milliseconds around committed stops mid-day.

DYNAMIC
📊

Benchmark-validated Quality

Tested against CVRPLIB and Solomon VRPTW standard instances. Published gap-to-optimal. No marketing claims.

OPEN RESULTS
🗺

Route Visualization

Request HTML/SVG output with any solve. Embed stop-by-stop maps in your ops dashboard or driver app.

SVG + HTML
🔌

Bring Your Own Distances

Pass a custom distance matrix (OSRM, Google, HERE) or let Raiden compute Euclidean. Zero map-provider lock-in.

FLEXIBLE
// pricing

Compute units.
Not stop units.

Industry first: you pay for CPU-seconds consumed, not stops or routes solved.
What's a compute unit? 1 CU = 1 CPU-second of solver time. Each solve has a 1 CU minimum (1-second time budget). A 30-second quality solve uses 30 CU; a 60-second solve uses 60 CU. The Starter plan's 500 CU covers roughly 500 solves/month.
// cost calculator

How many stops do you route per day?

1,000 stops/day
3
compute units/month
$0
estimated monthly cost
Starter
recommended plan

Based on 1 CU minimum per solve (1-second time budget). Actual usage scales with time limit — longer solves produce higher quality routes.

Starter
$0
/ month · 500 compute units included
  • 500 solves/month
  • Unlimited vehicles & routes
  • CVRP + VRPTW support
  • Full REST API access
  • Community Discord support
Start Free →
Scale
$499
/ month · 5,000 compute units · $0.12/CU overage
  • 5,000 solves/month included
  • Committed-stop locking API
  • Dynamic re-optimization
  • Webhook delivery callbacks
  • 99.9% uptime SLA
  • Email + Slack support
Start Scale →
Enterprise
Custom
Volume compute-unit pricing
  • Dedicated solver instances
  • On-prem deployment option
  • Custom time limits & seeds
  • Published benchmark audit
  • 99.99% uptime SLA
  • Dedicated SRE + Slack
Talk to Sales →
// get started

Your routes.
Your compute.
Your price.

No sales call. No per-stop shock. Start on the free tier and scale on compute alone.